pfc-mcp
Eliminates friction in DEM simulation workflows by enabling engineers to configure and execute complex particle flow simulations via conversational AI rather…
MCP server that connects AI agents to ITASCA's numerical modeling software — PFC, FLAC, 3DEC, MPoint, and MassFlow. Claude can browse engine documentation, run DEM simulations, and execute code through natural conversation, picking the engine via a software parameter. Documentation tools work standalone; running simulations requires a bridge script (addon.py) started inside the ITASCA engine GUI. Formerly published as pfc-mcp.
- Ask Claude to set up and run particle flow simulations without writing PFC code directly.
- Generate DEM particle configurations from text descriptions of material properties and geometry.
- Automate batch simulation runs with Claude adjusting parameters based on convergence results.
Eliminates friction in DEM simulation workflows by enabling engineers to configure and execute complex particle flow simulations via conversational AI rather than manual parameter entry, reducing iteration time and lowering barriers for non-experts.
Geotechnical and mining engineers running routine PFC simulations who need faster iteration cycles and lower technical overhead.
https://github.com/yusong652/itasca-mcp
By yusong652
How to Get It
claude mcp add itasca-mcp -- uvx itasca-mcp
Tip: Paste this into a Claude Code conversation. Verify command matches your Claude Code version.
Once it’s connected, paste this into Claude:
Set up and run particle flow simulations without writing PFC code directly
Trust Signals Auto-scanned
Data & Access
Reviewer notes
Auto-scanned review. These are observations, not a security certification.
Scored from trust signals (evidence-eval-v1): 68 GitHub stars; contributors unknown; last commit 0d ago; license MIT.
Things to check
- Scanned, not hands-on tested — this entry was auto-scanned from public metadata (GitHub metrics, license, security flags). No reviewer has run it, and no tool-specific limitations have been documented yet.
How to evaluate tools before deploying →
Data shown here comes from public APIs and automated scanning. Reviewer notes reflect one person's experience. This is not a security certification or legal recommendation. Always evaluate tools according to your own organization's policies.
Evaluation
Scored from trust signals (evidence-eval-v1): 68 GitHub stars; contributors unknown; last commit 0d ago; license MIT.